© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 62994
    Prev
    Next
    INDEX
    Explanations

    considered as or to be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¯ļæĦı
    -0.09
    赶ä¸Ĭ
    -0.09
    umu
    -0.09
    ehler
    -0.09
    åij¨æģ©æĿ¥
    -0.09
    æīĢèĩ´
    -0.09
    ä½ĵæ£Ģ
    -0.09
    /photos
    -0.09
    让æĤ¨
    -0.09
    西çľģ
    -0.09
    POSITIVE LOGITS
    æĺ¯ä¸Ģç§į
    0.09
    è¿ĻæŶåĢĻ
    0.09
    两åıª
    0.09
    æŃ£å¸¸çļĦ
    0.09
    alive
    0.09
    metic
    0.09
    ate
    0.08
    normal
    0.08
    ä¸ĢåĽ¢
    0.08
    æĺ¯ä»Ģä¹Īåij¢
    0.08
    Activations Density 0.035%

    No Known Activations